How to write Spark Dataframe into HBase? - scala

Question

I'm trying to write Spark Dataframe into the HBase and followed several other blogs and one among of them is this but it's not working.
However I can read the data from HBase successfully as Dataframe. Also some post has used org.apache.hadoop.hbase.spark format and others org.apache.spark.sql.execution.datasources.hbase. I'm not sure which one to use. Spark - 2.2.2; HBase - 1.4.7; Scala - 2.11.12 and Hortonworks SHC 1.1.0-2.1-s_2.11 from here.
The code is as follows:
case class UserMessageRecord(
rowkey: String,
Name: String,
Number: String,
message: String,
lastTS: String
)//this has been defined outside of the object scope
val exmple = List(UserMessageRecord("86325980047644033486","enrique","123455678",msgTemplate,timeStamp))
import spark.sqlContext.implicits._
val userDF = exmple.toDF()
//write to HBase
userDF.write
.options(Map(HBaseTableCatalog.tableCatalog -> catalog))
.format("org.apache.spark.sql.execution.datasources.hbase").save() //exception here
//read from HBase and it's working fine
def withCatalog(cat: String): DataFrame = {
spark.sqlContext
.read
.options(Map(HBaseTableCatalog.tableCatalog->cat))
.format("org.apache.spark.sql.execution.datasources.hbase")
.load()
}
val df = withCatalog(catalog)
df.show()
Here's the exception:
Exception in thread "main" java.lang.NullPointerException
at org.apache.hadoop.hbase.security.UserProvider.instantiate(UserProvider.java:122)
at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:214)
at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:119)
at org.apache.hadoop.hbase.mapreduce.TableOutputFormat.checkOutputSpecs(TableOutputFormat.java:177)
at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$.write(SparkHadoopMapReduceWriter.scala:76)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopDataset(PairRDDFunctions.scala:1084)
at org.apache.spark.sql.execution.datasources.hbase.HBaseRelation.insert(HBaseRelation.scala:218)
at org.apache.spark.sql.execution.datasources.hbase.DefaultSource.createRelation(HBaseRelation.scala:61)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:469)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:48)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:609)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at HbaseConnectionTest.HbaseLoadUsingSpark$.main(HbaseLoadUsingSpark.scala:85)
at HbaseConnectionTest.HbaseLoadUsingSpark.main(HbaseLoadUsingSpark.scala)

Answer 1

As discussed over here I made additional configuration changes to SparkSession builder and the exception is gone. However, I am not clear on the cause and the fix.
val spark: SparkSession = SparkSession.builder()
.master("local[1]")
.appName("HbaseSparkWrite")
.config("spark.hadoop.validateOutputSpecs", false)
.getOrCreate()